Frontiers in ML: Learning from Limited Labeled Data: Challenges and Opportunities for NLP

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=MD2fYFt5_5E


Category:
Let's Play
Duration: 1:34:19
1,103 views
22

Modern machine learning applications have enjoyed a great boost utilizing neural networks models, allowing them to achieve state-of-the-art results on a wide range of tasks. Such models, however, require large amounts of annotated data for training. In many real-world scenarios, such data is of limited availability making it difficult to translate these gains into real-world impact. Collecting large amounts of annotated data is often difficult or even infeasible due to the time and expense of labelling data and the private and personal nature of some of these datasets. This session will discuss several approaches to address the labelled data scarcity. In particular, the session will discuss work on: (1) transfer learning techniques that can transfer knowledge between different domains or languages to reduce the need for annotated data; (2) weakly-supervised learning where distant or heuristic supervision is derived from the data itself or other available metadata; (3) and techniques which learn from user interactions or other reward signals directly with techniques such as reinforcement learning. The discussion will be grounded on real-world applications where we aspire to bring AI experiences quickly and efficiently to everyone in more tasks, markets, languages, and domains.

Session Lead: Ahmed Hassan Awadallah, Microsoft

Speaker: Ahmed Hassan Awadallah, Microsoft
Talk Title: Bringing AI Experiences to Everyone

Speaker: Marti Hearst, University of California, Berkeley
Talk Title: Summarization without the Summaries

Speaker: Graham Neubig, Carnegie Mellon University
Talk Title: Lessons from the Long Tail: Methods for NLP in the Next 1,000 Languages

Speaker: Alex Ratner, University of Washington
Talk Title: ML Development with Weak Supervision: Notes from the Field

Q&A panel with all 4 speakers

See more on-demand sessions from Microsoft Research's Frontiers in Machine Learning 2020 virtual event: https://www.microsoft.com/en-us/research/event/frontiers-in-machine-learning-2020/



Other Videos By Microsoft Research


2020-07-30How Work From Home Affects Collaboration: Information Workers in a Natural Experiment During COVID19
2020-07-30Empowering and Supporting Remote Software Development Team Members through a Culture of Allyship
2020-07-30Impact of COVID-19 crisis on the future of work in India
2020-07-30Towards a Practical Virtual Office for Mobile Knowledge Workers
2020-07-30Challenges and Gratitude of Software Developers During COVID-19 Working From Home
2020-07-30Remote Work and Well-Being
2020-07-30Early Indicators of the Effect of the Global Shift to Remote Work on People with Disabilities
2020-07-29Hope Speech and Help Speech: Surfacing Positivity Amidst Hate
2020-07-28Frontiers in Machine Learning: Security and Machine Learning
2020-07-28Frontiers in Machine Learning: Climate Impact of Machine Learning
2020-07-28Frontiers in ML: Learning from Limited Labeled Data: Challenges and Opportunities for NLP
2020-07-28Frontiers in Machine Learning: Saving Lives with Interpretable ML
2020-07-28Frontiers in Machine Learning: Machine Learning Reliability and Robustness
2020-07-28Frontiers in Machine Learning: Big Ideas in Causality and Machine Learning
2020-07-28Frontiers in Machine Learning: Beyond Fairness: Pushing ML Frontiers for Social Equity [Panel]
2020-07-28Frontiers in Machine Learning: Accelerating Machine Learning with Confidential Computing
2020-07-28Frontiers in Machine Learning: Machine Learning Conversations
2020-07-28Frontiers in Machine Learning: Fireside Chat
2020-07-23Optics for the Cloud PhD Event 2020 - Day 2
2020-07-23Optics for the Cloud PhD Event 2020 - Day 1
2020-07-23Abstraction in Reinforcement Learning


Tags:
Frontiers in Machine Learning 2020
Microsoft Research
natural language processing
NLP
reinforcement learning
Ahmed Hassan Awadallah
Marti Hearst
Graham Neubig
Alex Ratner